Search Results for author:
Found 40 papers, 13 papers with code
D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detection
However, there are limited studies on adapting from the visible to the thermal domain, because the domain gap between the visible and thermal domains is much larger than expected, and traditional domain adaptation can not successfully facilitate learning in this situation.
PANDAS: Prototype-based Novel Class Discovery and Detection
In this work, we look at ways to extend a detector trained for a set of base classes so it can i) spot the presence of novel classes, and ii) automatically enrich its repertoire to be able to detect those newly discovered classes together with the base ones.
SoK: Facial Deepfake Detectors
Our systematized analysis and experimentation lay the groundwork for a deeper understanding of deepfake detectors and their generalizability, paving the way for future research focused on creating detectors adept at countering various attack scenarios.
Match me if you can: Semantic Correspondence Learning with Unpaired Images
Recent approaches for semantic correspondence have focused on obtaining high-quality correspondences using a complicated network, refining the ambiguous or noisy matching points.
Improving Lane Detection Generalization: A Novel Framework using HD Maps for Boosting Diversity
Lane detection is a vital task for vehicles to navigate and localize their position on the road.
Leveraging Future Relationship Reasoning for Vehicle Trajectory Prediction
We also model the interaction using a probabilistic distribution, which allows for multiple possible future interactions.
Ranked #2 on
Trajectory Prediction
on nuScenes
Deep Reinforcement Learning for Asset Allocation: Reward Clipping
Recently, there are many trials to apply reinforcement learning in asset allocation for earning more stable profits.
Trajectory Flow Map: Graph-based Approach to Analysing Temporal Evolution of Aggregated Traffic Flows in Large-scale Urban Networks
First, we partition the entire network into a set of cells based on the spatial distribution of data points in individual trajectories, where the cells represent spatial regions between which aggregated traffic flows can be measured.
A deep learning framework to generate realistic population and mobility data
Census and Household Travel Survey datasets are regularly collected from households and individuals and provide information on their daily travel behavior with demographic and economic characteristics.
ConMatch: Semi-Supervised Learning with Confidence-Guided Consistency Regularization
We present a novel semi-supervised learning framework that intelligently leverages the consistency regularization between the model's predictions from two strongly-augmented views of an image, weighted by a confidence of pseudo-label, dubbed ConMatch.
Estimating Link Flows in Road Networks with Synthetic Trajectory Data Generation: Reinforcement Learning-based Approaches
To ensure the generated population vehicle trajectories are consistent with the observed traffic volume and trajectory data, two methods based on Inverse Reinforcement Learning and Constrained Reinforcement Learning are proposed.
Joint Learning of Feature Extraction and Cost Aggregation for Semantic Correspondence
In this paper, we propose a novel framework for jointly learning feature extraction and cost aggregation for semantic correspondence.
Semi-Supervised Learning of Semantic Correspondence with Pseudo-Labels
In this paper, we present a simple, but effective solution for semantic correspondence that learns the networks in a semi-supervised manner by supplementing few ground-truth correspondences via utilization of a large amount of confident correspondences as pseudo-labels, called SemiMatch.
AggMatch: Aggregating Pseudo Labels for Semi-Supervised Learning
In this paper, we address this limitation with a novel SSL framework for aggregating pseudo labels, called AggMatch, which refines initial pseudo labels by using different confident instances.
A Computational Approach to Measure Empathy and Theory-of-Mind from Written Texts
Sentences that successfully take the perspective of others (the highest ToM level) were the most difficult to predict.
Transformer-based Map Matching Model with Limited Ground-Truth Data using Transfer-Learning Approach
In many spatial trajectory-based applications, it is necessary to map raw trajectory data points onto road networks in digital maps, which is commonly referred to as a map-matching process.
MLPD: Multi-Label Pedestrian Detector in Multispectral Domain
In this letter, we tackle multispectral pedestrian detection, where all input data are not paired.
Logit As Auxiliary Weak-supervision for More Reliable and Accurate Prediction
When a person identifies objects, he or she can think by associating objects to many classes and conclude by taking inter-class relations into account.
Associative Partial Domain Adaptation
Our Associative Partial Domain Adaptation (APDA) utilizes intra-domain association to actively select out non-trivial anomaly samples in each source-private class that sample-level weighting cannot handle.
TrajGAIL: Generating Urban Vehicle Trajectories using Generative Adversarial Imitation Learning
A generative model for urban vehicle trajectories can better generalize from training data by learning the underlying distribution of the training data and, thus, produce synthetic vehicle trajectories similar to real vehicle trajectories with limited observations.
Sample-based Regularization: A Transfer Learning Strategy Toward Better Generalization
However, this is likely to restrict the potential of the target model and some transferred knowledge from the source can interfere with the training procedure.
Restore from Restored: Single Image Denoising with Pseudo Clean Image
However, these methods have limitations in using internal information available in a given test image.
Restore from Restored: Video Restoration with Pseudo Clean Video
We analyze the restoration performance of the fine-tuned video denoising networks with the proposed self-supervision-based learning algorithm, and demonstrate that the FCN can utilize recurring patches without requiring accurate registration among adjacent frames.
Fast Adaptation to Super-Resolution Networks via Meta-Learning
In the training stage, we train the network via meta-learning; thus, the network can quickly adapt to any input image at test time.
Self-Supervised Fast Adaptation for Denoising via Meta-Learning
Under certain statistical assumptions of noise, recent self-supervised approaches for denoising have been introduced to learn network parameters without true clean images, and these methods can restore an image by exploiting information available from the given input (i. e., internal statistics) at test time.
Robust Nucleus Detection from Microscopical Image with Partially Labeled Exemplars
Quantitative analysis of cell nuclei in microscopic images is an essential yet still challenging source of biological and pathological information.
Key Instance Selection for Unsupervised Video Object Segmentation
After M-th frame, we select K IDs based on video saliency and frequency of appearance; then only these key IDs are tracked through the remaining frames.
Discriminative Few-Shot Learning Based on Directional Statistics
Metric-based few-shot learning methods try to overcome the difficulty due to the lack of training examples by learning embedding to make comparison easy.
Attention-based Recurrent Neural Network for Urban Vehicle Trajectory Prediction
With the increasing deployment of diverse positioning devices and location-based services, a huge amount of spatial and temporal information has been collected and accumulated as trajectory data.
Learning to Embed Semantic Correspondence for Natural Language Understanding
While learning embedding models has yielded fruitful results in several NLP subfields, most notably Word2Vec, embedding correspondence has relatively not been well explored especially in the context of natural language understanding (NLU), a task that typically extracts structured semantic knowledge from a text.
Doubly Nested Network for Resource-Efficient Inference
Slicing doubly nested network gives a working sub-network.
Auto-Meta: Automated Gradient Based Meta Learner Search
Fully automating machine learning pipelines is one of the key challenges of current artificial intelligence research, since practical machine learning often requires costly and time-consuming human-powered processes such as model design, algorithm development, and hyperparameter tuning.
Meta Continual Learning
This ability is limited in the current deep neural networks by a problem called catastrophic forgetting, where training on new tasks tends to severely degrade performance on previous tasks.
Unsupervised Visual Attribute Transfer with Reconfigurable Generative Adversarial Networks
To address the issue, we propose an unsupervised method to learn to transfer visual attribute.
End-to-end Learning of Image based Lane-Change Decision
We propose an image based end-to-end learning framework that helps lane-change decisions for human drivers and autonomous vehicles.
Continual Learning with Deep Generative Replay
Attempts to train a comprehensive artificial intelligence capable of solving multiple tasks have been impeded by a chronic problem called catastrophic forgetting.
Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
While humans easily recognize relations between data from different domains without any supervision, learning to automatically discover them is in general very challenging and needs many ground-truth pairs that illustrate the relations.
Ranked #10 on
Facial Expression Translation
on CelebA
Accurate Image Super-Resolution Using Very Deep Convolutional Networks
We present a highly accurate single-image super-resolution (SR) method.
Ranked #4 on
Image Super-Resolution
on WebFace - 8x upscaling
Deeply-Recursive Convolutional Network for Image Super-Resolution
We propose an image super-resolution method (SR) using a deeply-recursive convolutional network (DRCN).
Ranked #20 on
Image Super-Resolution
on Urban100 - 2x upscaling
Dual Memory Architectures for Fast Deep Learning of Stream Data via an Online-Incremental-Transfer Strategy
The proposed architecture consists of deep representation learners and fast learnable shallow kernel networks, both of which synergize to track the information of new data.
